Search Azure terms

AI and Machine Learning learning-path-anchor Synonym map A synonym map helps Azure AI Search understand that different words can mean the same thing for search. Users may type laptop, notebook, ultrabook, or a product nickname, while the indexed document uses only one of those terms. The synonym map teaches the search service to expand or rewrite the query so relevant documents... Azure AI Search intermediate 5 commands Aliases: AI Search synonym map, search synonyms, synonymMaps, equivalent terms map Quick peek Open full term page

AI and Machine Learning learning-path-anchor System message A system message is the instruction layer that tells an Azure OpenAI chat model how it should behave before it answers the user's request. It can define the assistant's role, tone, allowed sources, formatting rules, safety boundaries, and refusal behavior. It is stronger than an ordinary user message, but it is not magic and... Azure OpenAI fundamentals 5 commands Aliases: system prompt, metaprompt, developer instruction, assistant instruction Quick peek Open full term page

AI and Machine Learning learning-path-anchor Text to speech Text to speech in Azure AI Speech converts written text or SSML into synthesized audio using neural voices, custom voice options, language support, and APIs. Teams use it to add spoken responses to apps, contact centers, accessibility tools, devices, and media workflows while governing region, keys, networking, and quota. Azure AI services fundamentals 4 commands Aliases: Text to speech, text to speech, Azure Text to speech, Microsoft Learn Text to speech, TTS, speech synthesis, Azure AI Speech synthesis, neural voices, SSML speech Quick peek Open full term page

AI and Machine Learning command-rich Data source in AI Search Data source in AI Search is documented by Microsoft as part of the Azure AI Search area in Azure. Azure AI Search intermediate 6 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning command-rich Search admin key A search admin key is one of the generated API keys for an Azure AI Search service that allows full read-write data-plane access. It can create, update, or delete indexes, indexers, data sources, and documents, so it must be protected, rotated, and replaced with role-based access when possible. Azure AI Search fundamentals 5 commands Aliases: Azure AI Search admin key, search service admin key, Azure Search API admin key, primary admin key, secondary admin key Quick peek Open full term page

AI and Machine Learning premium Abuse monitoring Abuse monitoring is the safety layer that looks for harmful or policy-violating use of AI services. It is not a performance feature; it exists to help detect misuse, protect the service, and support responsible operation of model deployments. Azure OpenAI intermediate 4 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Admin key Admin key is an Azure AI Search API key with administrative access to the search service data plane. In everyday Azure work, teams use it to create, update, or delete indexes, indexers, data sources, skillsets, synonym maps, and query data when key-based access is enabled. The useful evidence is primary or secondary key, service name, Azure AI Search intermediate 4 commands Aliases: Azure AI Search admin key, Search service admin key, search admin API key Quick peek Open full term page

AI and Machine Learning premium Agent run Agent run is one execution of an agent against a thread, during which the agent reads messages, reasons, may call tools, and produces output. In everyday Azure work, teams use it to track what an agent attempted, what tools it used, whether it completed, and why a response was produced. The useful evidence is thread Microsoft Foundry intermediate 4 commands Aliases: Foundry agent run, AI agent run, thread run Quick peek Open full term page

AI and Machine Learning premium Agent service Agent service is Microsoft Foundry Agent Service, a managed platform for building, deploying, and scaling AI agents. In everyday Azure work, teams use it to create prompt agents, workflow agents, or hosted code-based agents that use models and tools to perform tasks. The useful evidence is project, agent ID, instructions, model, tool configuration, deployment type, Microsoft Foundry intermediate 4 commands Aliases: Microsoft Foundry Agent Service, Foundry Agent Service, Azure AI agent service Quick peek Open full term page

AI and Machine Learning premium Agent thread Agent thread is the persistent conversation state that stores messages and context used by an agent during runs. In everyday Azure work, teams use it to keep a multi-turn interaction organized so the agent can understand prior user messages and produce contextual responses. The useful evidence is thread ID, messages, metadata, related run IDs, timestamps, Microsoft Foundry intermediate 4 commands Aliases: Foundry agent thread, AI agent conversation thread, agent conversation context Quick peek Open full term page

AI and Machine Learning premium Agent tool Agent tool is a capability an agent can invoke to search, run code, query data, call APIs, or perform a configured action. In everyday Azure work, teams use it to let an agent go beyond text generation by grounding answers or carrying out controlled work. The useful evidence is tool type, configuration, authentication method, allowed Microsoft Foundry intermediate 4 commands Aliases: Foundry agent tool, AI agent tool, agent built-in tool, agent custom tool Quick peek Open full term page

AI and Machine Learning premium Agentic retrieval Agentic retrieval is an Azure AI Search retrieval pipeline that uses an LLM to plan focused subqueries for complex RAG questions. In everyday Azure work, teams use it to answer multi-part questions by decomposing the user request and chat history into targeted searches over indexed content. The useful evidence is knowledge base, knowledge source, search Azure AI Search intermediate 4 commands Aliases: Azure AI Search agentic retrieval, multi-query retrieval, agentic RAG retrieval Quick peek Open full term page

AI and Machine Learning premium AI connection AI connection is a Microsoft Foundry project connection that links the project to an external or Azure resource such as models, storage, search, or services. In everyday Azure work, teams use it to let AI applications and agents use approved resources without every prototype hardcoding endpoints and credentials. The useful evidence is connection name, target AI platform intermediate 4 commands Aliases: Foundry connection, AI project connection, connected resource, AI service connection Quick peek Open full term page

AI and Machine Learning premium AI evaluation AI evaluation is the Microsoft Foundry process of testing a generative AI model, agent, or application against a dataset and measuring its quality, safety, and task performance with built-in or custom evaluators. Microsoft Foundry intermediate 3 commands Aliases: Azure AI evaluation, Foundry evaluation, generative AI evaluation, model evaluation Quick peek Open full term page

AI and Machine Learning premium AI quota AI quota is the Azure allocation that limits model deployment capacity, usually by subscription, region, model, and deployment type, using measures such as tokens per minute, requests per minute, concurrent requests, or provisioned throughput. Microsoft Foundry intermediate 3 commands Aliases: Foundry quota, Azure OpenAI quota, model quota, TPM quota, RPM quota Quick peek Open full term page

AI and Machine Learning premium AI red teaming AI red teaming is the practice of probing a generative AI system with adversarial prompts, attack strategies, and risk categories to discover unsafe behavior, jailbreak weaknesses, and harmful-output paths before or after deployment. Responsible AI advanced 3 commands Aliases: AI Red Teaming Agent, red team scan, adversarial AI testing, LLM red teaming Quick peek Open full term page

AI and Machine Learning premium AI service endpoint An AI service endpoint is the HTTPS base address that applications use to call an Azure AI or Foundry Tools resource. It identifies the resource, region or custom subdomain, and may resolve through public DNS or a private endpoint. Azure AI services fundamentals 3 commands Aliases: Azure AI endpoint, Cognitive Services endpoint, Foundry Tools endpoint, AI resource URL Quick peek Open full term page

AI and Machine Learning premium AI service key An AI service key is a secret access key for an Azure AI service resource. Clients pass it, commonly with the Ocp-Apim-Subscription-Key header, to authenticate API requests when key-based authentication is used. Azure AI services fundamentals 3 commands Aliases: Azure AI service key, Cognitive Services key, Ocp-Apim-Subscription-Key, resource key Quick peek Open full term page

AI and Machine Learning premium AI services account key An AI services account key is a secret key for a multi-service Azure AI or Microsoft Foundry resource. It can authenticate requests for supported services tied to that resource, making storage, rotation, and access control especially important. Azure AI services intermediate 3 commands Aliases: multi-service account key, Foundry resource key, AIServices account key, Cognitive Services account key Quick peek Open full term page

AI and Machine Learning premium AI services endpoint An AI services endpoint is the base URL for a multi-service Azure AI or Microsoft Foundry resource. Applications combine this endpoint with a supported API path and authentication method to call the resource. Azure AI services fundamentals 3 commands Aliases: multi-service endpoint, Foundry resource endpoint, AIServices endpoint, Cognitive Services endpoint Quick peek Open full term page

AI and Machine Learning premium AI services resource An AI services resource is the Azure resource, commonly Microsoft.CognitiveServices/accounts with kind AIServices, that provides the governance scope for AI service access, networking, billing, monitoring, keys, endpoints, model deployments, projects, and related configuration. Azure AI services fundamentals 3 commands Aliases: Azure AI services resource, Foundry resource, AIServices resource, Cognitive Services account Quick peek Open full term page

AI and Machine Learning premium AI token An AI token is a unit of text processed by a language model. Azure AI and Foundry model quotas, cost, and rate limits commonly use tokens to measure prompt input, generated output, and throughput such as tokens per minute. Azure OpenAI and Foundry Models fundamentals 3 commands Aliases: model token, LLM token, input token, output token, TPM Quick peek Open full term page

AI and Machine Learning premium AI tracing AI tracing captures execution telemetry for generative AI applications and agents, including model calls, prompts, tool invocations, retrieval steps, latency, token usage, errors, and run relationships so teams can debug and monitor behavior in Microsoft Foundry and Azure Monitor. AI observability intermediate 3 commands Aliases: Foundry tracing, agent tracing, LLM tracing, AI distributed tracing Quick peek Open full term page

AI and Machine Learning premium Analyze Analyze is the Azure AI Search operation that shows how a selected analyzer breaks supplied text into tokens for an index. Text analysis intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Analyzer An analyzer in Azure AI Search processes text during indexing and querying by applying character filters, tokenizers, and token filters. Text analysis intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Assistant message Assistant message is the conversation record produced inside an Assistants-style workflow. In the classic Assistants API model, messages live on a thread and can come from a user or the assistant. For operators, the important point is that an assistant message is not just screen text; it is state that may be stored, retrieved. Azure OpenAI intermediate 2 commands Aliases: Assistants API message, thread message, assistant-generated message, Azure OpenAI assistant message Quick peek Open full term page

AI and Machine Learning premium Assistants API Assistants API is the older assistant-building API pattern that organizes an AI workflow around assistants, threads, messages, runs, tools, and files. It helped developers build stateful assistants without inventing every orchestration object themselves. In 2026, it should be treated as a migration-sensitive term because Azure documentation marks the classic Assistants API as deprecated and. Azure OpenAI intermediate 2 commands Aliases: Azure OpenAI Assistants API, OpenAI Assistants API, classic Assistants API, Assistants API v2 Quick peek Open full term page

AI and Machine Learning premium Autocomplete Autocomplete is the search-box behavior where Azure AI Search finishes what a user is typing. In plain terms, if someone starts entering “seat,” the system can offer a completed term such as “seattle” before the full search is submitted. It works from fields registered in a suggester, not from random database guessing. Teams use it to. Azure AI Search intermediate 4 commands Aliases: Azure AI Search autocomplete, typeahead, search-as-you-type, suggester autocomplete Quick peek Open full term page

AI and Machine Learning premium AutoML AutoML is Azure Machine Learning’s way to automate much of the model-search process. In plain terms, you tell Azure what problem you are solving, provide labeled data, choose a metric, and set limits. The service tries different model pipelines and reports which candidates performed best. It helps teams move faster when they need a. Azure Machine Learning intermediate 4 commands Aliases: automated ML, Azure Machine Learning AutoML, automated machine learning, AutoML job Quick peek Open full term page

AI and Machine Learning premium Azure AI Content Safety Azure AI Content Safety is the Azure AI service used to detect harmful text and image content before it reaches users, moderators, or automated workflows. In Azure, teams encounter it when applications accept user posts, comments, uploads, prompts, or model outputs that need moderation and policy review. The useful question is what behavior it proves, Responsible AI advanced 4 commands Aliases: Content Safety, Azure Content Safety, harm detection, content moderation API Quick peek Open full term page

AI and Machine Learning premium Azure AI Foundry Create a governed project boundary where AI teams can build agents, evaluations, files, and model deployments without unmanaged sprawl.; Compare, evaluate, and approve model deployments before a generative AI feature is AI platform fundamentals 5 commands Aliases: AI Foundry, Microsoft Foundry, Foundry resource, Foundry project, Azure AI Foundry, azure ai foundry Quick peek Open full term page

AI and Machine Learning premium Azure AI Foundry hub Azure AI Foundry hub is the classic Foundry hub resource used to group AI projects that share common security, data access, connections, and platform settings. In Azure, teams encounter it when teams need hub-based projects for selected Foundry and Azure Machine Learning scenarios such as fine-tuning, shared connections, and custom ML work. The useful question AI platform advanced 4 commands Aliases: AI Hub, Foundry AI Hub, hub-based project, Azure AI hub Quick peek Open full term page

AI and Machine Learning premium Azure AI Foundry project An Azure AI Foundry project is the working area where a team builds and organizes an AI application inside Microsoft Foundry. It keeps related agents, evaluations, files, indexes, tools, connections, and model usage together instead of scattering them across a shared portal. Think of it as the project boundary for one AI product, prototype, or team. It is useful because AI work quickly becomes messy: prompts, test data, model deployments, safety checks, and access decisions all need a home with ownership and repeatable operations. AI platform advanced 4 commands Aliases: AI Foundry project, AI project, Foundry project, Microsoft Foundry project Quick peek Open full term page

AI and Machine Learning premium Azure AI Language Azure AI Language is the Azure natural-language processing service for analyzing and understanding text with prebuilt and customizable language capabilities. AI services intermediate 4 commands Aliases: Azure Language, Azure Language in Foundry Tools, Azure Language service, Language in Foundry Tools, Language service Quick peek Open full term page

AI and Machine Learning premium Azure AI metrics Azure AI metrics is the measurable signals used to observe Azure AI applications, model endpoints, agents, evaluations, safety checks, and business outcomes. Azure AI services intermediate 4 commands Aliases: AI metrics, AI service metrics, Azure AI Metrics Advisor, Azure Monitor metrics for AI, Metrics Advisor, time series anomaly detection Quick peek Open full term page

AI and Machine Learning premium Azure AI Search Azure AI Search is a managed retrieval service for full-text, vector, hybrid, and semantic search across application and enterprise content. It provides search services, indexes, indexers, skillsets, ranking features, security controls, and APIs used by apps, copilots, and knowledge portals. Search fundamentals 4 commands Aliases: Azure AI Search, AI Search, Azure Cognitive Search, enterprise search, vector search, hybrid search, semantic search, Search service Quick peek Open full term page

AI and Machine Learning premium Azure AI Search data source Azure AI Search data source is the connection definition an Azure AI Search indexer uses to read content from a supported external data store. AI platform and search intermediate 4 commands Aliases: Search data source, SearchIndexerDataSourceConnection, data source connection, indexer data source, search data source connection Quick peek Open full term page

AI and Machine Learning premium Azure AI Search index An Azure AI Search index is the place where your application searches. It is not just a pointer to a database or blob container. It is a separate searchable structure with documents, fields, and rules for how text, filters, facets, semantic ranking, and vectors behave. If the index schema is wrong, the search experience feels wrong even when the source data is good. Developers and operators use indexes to make. AI platform and search intermediate 5 commands Aliases: Azure AI Search index, search index, AI Search index, azure-ai-search-index Quick peek Open full term page

AI and Machine Learning premium Azure AI Search indexer An Azure AI Search indexer is the automated worker that fills a search index from another data source. Instead of your application pushing every document into Azure AI Search, the indexer pulls from places such as Blob Storage, Azure SQL, Cosmos DB, or Data Lake Storage. It can map fields, detect changes, crack documents, and run enrichment skills before writing searchable documents. It is useful when source data changes regularly. AI platform and search intermediate 5 commands Aliases: Azure AI Search indexer, search indexer, indexer, azure-ai-search-indexer Quick peek Open full term page

AI and Machine Learning premium Azure AI Search service Azure AI Search service is the Azure resource that hosts Azure AI Search indexes, indexers, skillsets, keys, capacity, networking, and query endpoints. AI platform and search intermediate 4 commands Aliases: AI Search resource, AI Search service, Azure Search service, Search service, search service Quick peek Open full term page

AI and Machine Learning premium Azure AI Search skillset Azure AI Search skillset is a reusable Azure AI Search enrichment object that applies built-in or custom processing during indexer execution. AI platform and search intermediate 4 commands Aliases: AI enrichment skillset, Search skillset, cognitive skillset, skillset Quick peek Open full term page

AI and Machine Learning premium Azure AI services Azure AI services is the family of Azure cloud AI APIs and resources, surfaced through Foundry Tools, for vision, speech, language, translation, content, and generative scenarios. AI services fundamentals 4 commands Aliases: AI services, Azure AI services account, Cognitive Services, Foundry Tools Quick peek Open full term page

AI and Machine Learning premium Azure AI services account An Azure resource that provides endpoints, keys, identity, networking, billing, and monitoring for one or more Azure AI service capabilities. Azure AI services fundamentals 4 commands Aliases: AI services account, Azure AI multi-service resource, Foundry resource, Microsoft.CognitiveServices account Quick peek Open full term page

AI and Machine Learning premium Azure AI Speech The Azure speech service for converting speech to text, text to speech, speech translation, pronunciation assessment, and related speech-enabled capabilities. AI services intermediate 4 commands Aliases: Azure Speech, Speech in Foundry Tools, Speech service, Speech-to-text Quick peek Open full term page

AI and Machine Learning premium Azure AI Translator A cloud-based machine translation service for translating text and documents across supported languages through REST APIs and client libraries. AI services intermediate 4 commands Aliases: Azure Translator, Document Translation, Text Translation, Translator Quick peek Open full term page

AI and Machine Learning premium Azure AI Vision The Azure vision service that analyzes images and visual content for tasks such as OCR, object information, captions, tags, and image understanding. AI services intermediate 4 commands Aliases: Azure Vision, Computer Vision, Image Analysis, Vision in Foundry Tools Quick peek Open full term page

AI and Machine Learning premium Azure Machine Learning Azure Machine Learning is a cloud service for managing the machine learning lifecycle, including workspaces, data, training jobs, model deployment, monitoring, and MLOps. Machine learning operations advanced 5 commands Aliases: Azure ML, AML, Machine Learning workspace Quick peek Open full term page

AI and Machine Learning premium Azure OpenAI Azure OpenAI provides OpenAI model capabilities through Azure resources, deployments, identity, networking, quota, and monitoring controls. Azure OpenAI intermediate 8 commands Aliases: Azure OpenAI Service Quick peek Open full term page

AI and Machine Learning premium Azure OpenAI managed identity Azure OpenAI managed identity uses Microsoft Entra identities so Azure workloads can call model endpoints without stored keys. Azure OpenAI intermediate 5 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Azure OpenAI resource An Azure OpenAI resource is the Azure control-plane boundary that hosts deployments, endpoints, access, networking, and billing context. Azure OpenAI fundamentals 12 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Azure OpenAI Service Azure OpenAI Service provides managed access to OpenAI model capabilities through Azure endpoints and enterprise controls. Generative AI fundamentals 11 commands Aliases: Azure OpenAI Quick peek Open full term page

AI and Machine Learning premium Batch deployment A batch deployment in Azure Machine Learning is the deployment configuration behind a batch endpoint, defining the model or pipeline, compute, environment, and execution behavior for asynchronous inference. Azure Machine Learning intermediate 5 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Batch endpoint An Azure Machine Learning batch endpoint is an endpoint for long-running asynchronous inferencing that receives input data references, starts a batch job, and writes outputs for later use. Machine learning advanced 5 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Batch inference Batch inference is the process of generating predictions over larger sets of input data asynchronously, often using Azure Machine Learning batch endpoints and deployments. Azure OpenAI fundamentals 4 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium BM25 BM25 is the Azure AI Search full-text relevance scoring algorithm that ranks keyword search results using term frequency, inverse document frequency, length normalization, and saturation controls. Azure AI Search intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium BM25 ranking BM25 ranking is the ordering of Azure AI Search full-text results by BM25 relevance scores for searchable text fields and query terms. Azure AI Search fundamentals 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Bounding region A bounding region is Document Intelligence output that identifies an element location by page number and polygon coordinates on the page. Document Intelligence fundamentals 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Chat completion A AI platform capability in Azure OpenAI that helps teams build, secure, observe, and govern intelligent applications with clearer ownership, safety, and operational context. Azure OpenAI fundamentals 5 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Chat completions Chat completions are API calls to chat-capable models where the client sends role-based messages and receives the next model response, commonly through Azure OpenAI or Microsoft Foundry endpoints. Azure OpenAI intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Chunking Chunking is the process of splitting large documents into smaller text units for indexing, retrieval, embeddings, and downstream AI processing. AI platform and search intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Code interpreter tool An agent tool that can execute code for analysis tasks. AI platform and search intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Cognitive services account key A key used to authenticate to an Azure AI services resource. AI platform and search intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Cognitive skill A AI platform capability in Azure AI Search that helps teams build, secure, observe, and govern intelligent applications with clearer ownership, safety, and operational context. Azure AI Search fundamentals 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Completion the generated text or structured output returned by an AI model after an application sends prompt, message, or inference request data Azure OpenAI Intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Composed document model an Azure AI Document Intelligence model that combines several custom document models behind one model identifier so different document types can be analyzed together Document Intelligence Intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Compute cluster a managed Azure Machine Learning pool of CPU or GPU nodes that runs training, batch inference, and other jobs for a workspace Machine learning Intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Compute instance a managed Azure Machine Learning cloud workstation used by one data scientist or engineer for notebooks, experimentation, development, and lightweight testing Azure Machine Learning Beginner 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Computer Vision the Azure AI capability that helps applications understand images, read text, detect visual features, and return structured insights from pictures or screenshots Azure AI services fundamentals 12 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Confidence score a model-provided certainty value that helps teams judge whether extracted fields, text, tables, or classifications should be accepted automatically or reviewed by a person Document Intelligence fundamentals 5 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Content filter the safety configuration that evaluates model inputs and outputs and blocks or annotates harmful content according to policy Responsible AI intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Content filter result the response signal that tells an application what content category was detected and whether the content was filtered Responsible AI advanced 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Content Safety the Azure AI service used to detect harmful text and image content before it reaches users or workflows Responsible AI intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Content Understanding Content Understanding is documented by Microsoft as part of the Azure AI services area in Azure. Azure AI services intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Context window The amount of input and output text a model can process in one request. Generative AI advanced 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Conversational language understanding A AI platform capability in Azure AI services that helps teams build, secure, observe, and govern intelligent applications with clearer ownership, safety, and operational context. Azure AI services fundamentals 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Custom analyzer an Azure AI Search text-processing recipe built from character filters, a tokenizer, and token filters instead of using only a built-in analyzer. Azure AI Search fundamentals 4 commands Aliases: Azure AI Search custom analyzer, search custom analyzer, custom text analyzer Quick peek Open full term page

AI and Machine Learning premium Custom document model an Azure AI Document Intelligence model trained or built for a team’s specific document layout, fields, and extraction needs. Document Intelligence fundamentals 4 commands Aliases: Document Intelligence custom model, custom extraction model, custom neural document model Quick peek Open full term page

AI and Machine Learning premium Custom question answering an Azure AI Language capability for building a project that answers user questions from curated sources, question pairs, and deployed knowledge bases. Azure AI Language fundamentals 3 commands Aliases: CQA, Azure AI Language custom question answering, question answering project Quick peek Open full term page

AI and Machine Learning premium Custom Vision an Azure AI service for building, training, publishing, and improving custom image classification models from labeled images. Azure AI Vision fundamentals 4 commands Aliases: Azure AI Custom Vision, Custom Vision Service, custom image classifier Quick peek Open full term page

AI and Machine Learning premium Data drift A measurable change in production input data or feature distributions compared with the baseline data used to train or validate a model. Model monitoring and MLOps Intermediate 4 commands Aliases: feature drift, input data drift, model data drift Quick peek Open full term page

AI and Machine Learning premium Deployment capacity Deployment capacity is the throughput allocation configured for an Azure OpenAI or Foundry model deployment, affecting available request volume, quota use, latency, and cost. Azure OpenAI intermediate 4 commands Aliases: Azure OpenAI deployment capacity, model deployment capacity, deployment throughput capacity, PTU deployment capacity Quick peek Open full term page

AI and Machine Learning premium Deployment type Deployment type is the Azure AI or Microsoft Foundry model hosting option, such as standard, global, data-zone, regional, batch, serverless, or provisioned deployment, that determines availability, data processing location, capacity model, cost, and operational behavior. Microsoft Foundry intermediate 4 commands Aliases: Microsoft Foundry deployment type, Azure AI deployment type, model deployment type, Foundry Models deployment type Quick peek Open full term page

AI and Machine Learning premium Document analysis operation A document analysis operation is an asynchronous Document Intelligence request that analyzes a document with a model and returns extracted content, layout, and fields when polling completes. Document Intelligence intermediate 5 commands Aliases: Analyze operation, analyze document operation, Document Intelligence analysis request, async analysis operation Quick peek Open full term page

AI and Machine Learning premium Document classifier A document classifier is a Document Intelligence custom classification model that identifies document types or pages before extraction and routing. Document Intelligence intermediate 5 commands Aliases: custom classifier, Document Intelligence classifier, classification model, page classifier Quick peek Open full term page

AI and Machine Learning premium Document field A document field is a structured value extracted by Document Intelligence, usually with field type, content, confidence, and location metadata in the analyze result. Document Intelligence fundamentals 5 commands Aliases: extracted field, field value, query field, document result field Quick peek Open full term page

AI and Machine Learning premium Document Intelligence Azure AI Document Intelligence is a cloud service that uses OCR and machine learning to extract text, layout, tables, key-value pairs, and fields from documents. Document Intelligence fundamentals 5 commands Aliases: Azure AI Document Intelligence, Azure Document Intelligence, Form Recognizer, intelligent document processing Quick peek Open full term page

AI and Machine Learning premium Document Intelligence custom model A Document Intelligence custom model is a trained model built from representative labeled documents to extract fields from organization-specific document types. Document Intelligence intermediate 5 commands Aliases: custom extraction model, custom neural model, custom template model, trained custom document model Quick peek Open full term page

AI and Machine Learning premium Document Intelligence layout model The Document Intelligence layout model is a prebuilt model that extracts document text, tables, selection marks, structure, and layout information without custom training. Document Intelligence fundamentals 5 commands Aliases: layout model, prebuilt layout model, document layout analysis, layout analysis model Quick peek Open full term page

AI and Machine Learning premium Document Intelligence model A Document Intelligence model is a prebuilt, custom, composed, or classifier model used to analyze documents and return structured extraction or classification results. Document Intelligence fundamentals 5 commands Aliases: document model, prebuilt model, custom model, model ID Quick peek Open full term page

AI and Machine Learning premium Document Intelligence resource A Document Intelligence resource is the Azure AI service resource that provides the endpoint, keys, region, pricing tier, network configuration, and monitoring for Document Intelligence APIs. Document Intelligence fundamentals 5 commands Aliases: Azure Document Intelligence resource, Document Intelligence account, AI service resource, Form Recognizer resource Quick peek Open full term page

AI and Machine Learning premium Embedding An embedding is a list of numbers that captures meaning in a way software can compare. Instead of matching only exact words, an application can compare the embedding for a user question with embeddings for documents, products, tickets, or records. Similar ideas end up near each other in vector space even when the wording differs. In Azure, embeddings commonly come from Azure OpenAI models and are stored in vector indexes. Generative AI fundamentals 4 commands Aliases: Embedding, text embedding, vector embedding, embedding vector, embedding Quick peek Open full term page

AI and Machine Learning premium Embedding model An embedding model converts text into numerical vector form so applications can perform text similarity, retrieval, and other semantic comparison tasks. Azure OpenAI intermediate 4 commands Aliases: text embedding model, Azure OpenAI embedding model, vector embedding model Quick peek Open full term page

AI and Machine Learning premium Embeddings Embeddings are the many vectors your system creates when it turns a collection of text, records, or documents into searchable meaning. One embedding represents one input or chunk; embeddings as a set become a retrieval layer. Applications compare a new query embedding against stored embeddings to find similar content. In Azure workloads, embeddings often connect Azure OpenAI model deployments with Azure AI Search, Cosmos DB, Azure SQL, PostgreSQL, or Redis.. Azure OpenAI fundamentals 4 commands Aliases: Embeddings, text embeddings, vector embeddings, embedding vectors, embeddings Quick peek Open full term page

AI and Machine Learning premium Embeddings model An embeddings model is a deployed model used to convert text into vector representations for semantic similarity, retrieval, and vector search workloads. Azure OpenAI intermediate 4 commands Aliases: embedding model deployment, embeddings deployment, text embeddings model Quick peek Open full term page

AI and Machine Learning premium Endpoint traffic split Azure Machine Learning online endpoints can allocate percentages of live traffic across deployments and can mirror traffic to validate a new deployment before full rollout. Azure Machine Learning intermediate 4 commands Aliases: online endpoint traffic split, traffic allocation, blue green endpoint split Quick peek Open full term page

AI and Machine Learning premium Enrichment cache An enrichment cache stores outputs from document cracking and skill execution in Azure Storage so AI enrichment pipelines can reuse existing processed content. Azure AI Search intermediate 4 commands Aliases: AI Search enrichment cache, incremental enrichment cache, skillset cache Quick peek Open full term page

AI and Machine Learning premium Exhaustive KNN Exhaustive KNN is a vector search algorithm that calculates distances across all candidate vectors to return the exact nearest neighbors for a query. Teams use it to test vector relevance, produce exact nearest-neighbor baselines, or serve smaller vector workloads where accuracy matters more than approximate search speed. It is not HNSW approximate search, semantic ranking, a text analyzer, an embedding model, or a fix for poor chunking and low-quality vectors. In production, confirm index schema, vector dimensions, algorithm configuration, vector profile, query k value, exhaustive flag, latency, throttling, relevance test set, and comparison with HNSW results before treating the design. Azure AI Search advanced 6 commands Aliases: exhaustive k-nearest neighbors, brute-force vector search, exhaustive vector search Quick peek Open full term page

AI and Machine Learning premium Experiment An Experiment in Azure Machine Learning groups related runs so parameters, metrics, artifacts, models, and lineage can be tracked and compared. Teams use it to organize model training, evaluation, and tuning work so teams can compare runs and reproduce how a model version was produced. It is not a deployed endpoint, a registered model, a notebook file, a compute cluster, or proof that a model is fair, secure, or production-ready. In production, confirm workspace, experiment name, run IDs, parameters, metrics, artifacts, data version, environment, compute target, model registration, owner, and promotion criteria before treating the design as healthy or ready. Machine learning intermediate 6 commands Aliases: Azure ML experiment, MLflow experiment, machine learning experiment Quick peek Open full term page

AI and Machine Learning premium Face API The Face API is an Azure AI service API that provides face detection, recognition, verification, identification, grouping, and related face analysis capabilities. Teams use it to build applications that detect faces in images, compare faces, verify identity scenarios, support liveness workflows, or organize face-related image data under approved responsible AI controls. It is not a general computer vision labeler, proof of identity by itself, a surveillance policy, or permission to use biometric capabilities without legal, privacy, and access review. Azure AI services intermediate 6 commands Aliases: Azure AI Face, Azure Face API, Face service Quick peek Open full term page

AI and Machine Learning premium Face service Face service is an Azure AI service that provides APIs for face detection, face analysis, verification, identification, grouping, and liveness-related workflows under approved access controls. Teams use it to build applications that detect faces in images, compare face evidence, verify approved identity scenarios, support liveness checks, or manage face lists within privacy and responsible AI controls. It is not a general image classification service, legal approval to process biometric data, a replacement for human identity review, or a guarantee that every face decision is correct. Azure AI services intermediate 6 commands Aliases: Azure AI Face, Azure AI Face service, Azure Face service, Face API, Azure AI services Face Quick peek Open full term page